Submission

Put the ipynb file and html file in the github branch you created in the last assignment and submit the link to the commit in brightspace

from plotly.offline import init_notebook_mode
import plotly.io as pio
import plotly.express as px

init_notebook_mode(connected=True)
pio.renderers.default = "plotly_mimetype+notebook"

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

Question 1:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

df_2007 = df[df["year"] == 2007]
df_2007 = df_2007.groupby("continent").sum()
print(df_2007["pop"].head())
print(df_2007.columns)

fig = px.bar(df_2007["pop"], color=df_2007.index, orientation="h", text_auto='.3s')
fig.show()

# YOUR CODE HERE

continent
Africa       929539692
Americas     898871184
Asia        3811953827
Europe       586098529
Oceania       24549947
Name: pop, dtype: int64
Index(['year', 'lifeExp', 'pop', 'gdpPercap', 'iso_num'], dtype='object')

Question 2:

Sort the order of the continent for the visualisation

Hint: Use axis layout setting

fig.update_layout(yaxis={'categoryorder':'total ascending'})
fig.show()

Question 3:

Add text to each bar that represents the population

fig.show()

Question 4:

Thus far we looked at data from one year (2007). Lets create an animation to see the population growth of the continents through the years

df_grouped = df.groupby(["continent","year"]).sum()
print(df_grouped.head(20))

df_grouped = df_grouped.reset_index(level=[0,1])
print(df_grouped.head(20))

fig = px.bar(df_grouped, y="continent", x="pop", animation_frame="year", range_x=[0,4000000000], orientation="h", color="continent")
fig.update_layout(yaxis={'categoryorder':'total ascending'})

fig.show()


# YOUR CODE HERE

                 lifeExp        pop      gdpPercap  iso_num
continent year                                             
Africa    1952  2035.046  237640501   65133.768223    23859
          1957  2145.850  264837738   72032.275237    23859
          1962  2252.611  296516865   83100.098892    23859
          1967  2357.396  335289489  106618.917645    23859
          1972  2467.449  379879541  121660.015058    23859
          1977  2578.182  433061021  134468.802440    23859
          1982  2682.829  499348587  129042.833907    23859
          1987  2773.929  574834110  118698.787546    23859
          1992  2788.738  659081517  118654.137329    23859
          1997  2787.110  743832984  123695.496865    23859
          2002  2772.912  833723916  135168.028262    23859
          2007  2849.914  929539692  160629.695446    23859
Americas  1952  1331.996  345152446  101976.563805     9843
          1957  1399.007  386953916  115401.093329     9843
          1962  1459.969  433270254  122538.546760     9843
          1967  1510.273  480746623  141706.337401     9843
          1972  1559.873  529384210  162283.353476     9843
          1977  1609.789  578067699  183800.178157     9843
          1982  1655.721  630290920  187668.427202     9843
          1987  1702.268  682753971  194835.006528     9843
   continent  year   lifeExp        pop      gdpPercap  iso_num
0     Africa  1952  2035.046  237640501   65133.768223    23859
1     Africa  1957  2145.850  264837738   72032.275237    23859
2     Africa  1962  2252.611  296516865   83100.098892    23859
3     Africa  1967  2357.396  335289489  106618.917645    23859
4     Africa  1972  2467.449  379879541  121660.015058    23859
5     Africa  1977  2578.182  433061021  134468.802440    23859
6     Africa  1982  2682.829  499348587  129042.833907    23859
7     Africa  1987  2773.929  574834110  118698.787546    23859
8     Africa  1992  2788.738  659081517  118654.137329    23859
9     Africa  1997  2787.110  743832984  123695.496865    23859
10    Africa  2002  2772.912  833723916  135168.028262    23859
11    Africa  2007  2849.914  929539692  160629.695446    23859
12  Americas  1952  1331.996  345152446  101976.563805     9843
13  Americas  1957  1399.007  386953916  115401.093329     9843
14  Americas  1962  1459.969  433270254  122538.546760     9843
15  Americas  1967  1510.273  480746623  141706.337401     9843
16  Americas  1972  1559.873  529384210  162283.353476     9843
17  Americas  1977  1609.789  578067699  183800.178157     9843
18  Americas  1982  1655.721  630290920  187668.427202     9843
19  Americas  1987  1702.268  682753971  194835.006528     9843

Question 5:

Instead of the continents, lets look at individual countries. Create an animation that shows the population growth of the countries through the years

# YOUR CODE HERE
df = px.data.gapminder()
fig = px.bar(df, y="country", x="pop", animation_frame="year", animation_group="country", color="continent", hover_name="country",
        range_x=[0,1500000000])

fig.update_layout(barmode='stack', yaxis={'categoryorder':'total descending'})
fig.show()

Question 6:

Clean up the country animation. Set the height size of the figure to 1000 to have a better view of the animation

# YOUR CODE HERE
fig.update_layout(height=1000)
fig.show()

Question 7:

Show only the top 10 countries in the animation

Hint: Use the axis limit to set this.

# YOUR CODE HERE
fig.update_layout(yaxis_range=[-0.5,9.5], height=400)
fig.show()